© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 128744
    Prev
    Next
    INDEX
    Explanations

    ocular following responses

    np_acts-logits-general · gemini-2.5-flash-lite

    words related to medical or biochemical terminology, particularly in scientific contexts.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    玙
    -2.73
    メニューは
    -2.58
    xFC
    -2.47
     (‘
    -2.47
     inhabit
    -2.38
    ⩥
    -2.33
    ↵
    -2.31
    !’
    -2.28
     целом
    -2.25
    闳
    -2.25
    POSITIVE LOGITS
    s
    4.19
    You
    3.08
    "
    3.02
    ной
    2.95
    та
    2.70
    ↵↵
    2.59
    ?"
    2.55
    ２
    2.52
    Your
    2.52
    的
    2.50
    Activations Density 0.008%

    No Known Activations